liu.seSearch for publications in DiVA
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Strategies for Accurate Context Retrieval in Retrieval-Augmented Generation Systems Across Diverse Datasets
Linköping University, Department of Computer and Information Science.
Linköping University, Department of Computer and Information Science.
2024 (English)Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE creditsStudent thesisAlternative title
Strategier för träffsäker kontextåtkomst i system för Retrieval-Augmented Generation över heterogena datamängder (Swedish)
Abstract [en]

In recent years, the rapid advancement of generative artificial intelligence has significantly expanded the horizons of knowledge management and information retrieval. With the increasing reliance on large language models across various domains, the efficiency of context retrieval for RAG systems has become a key part of leveraging these technologies. This thesis specifically addresses the optimization of context retrieval in RAG systems, concentrating on datasets with distinct linguistic attributes such as written and spoken language. The study’s findings indicate that organizing the knowledge base according to the nature of the language (written vs. spoken) of documents enhances retrieval accuracy. Furthermore, fine-tuning source-specific embedding models proves effective in bridging performance gaps among data sources. Additionally, the research unveils promising synergies between generating alternative queries and re-ranking retrieved context using large language models, innovations primarily explored in isolation in prior literature.

Place, publisher, year, edition, pages
2024. , p. 56
Keywords [en]
natural language processing, machine learning, artificial intelligence, retrieval-augmented generation
National Category
Natural Language Processing
Identifiers
URN: urn:nbn:se:liu:diva-205279ISRN: LIU-IDA/LITH-EX-A--24/028--SEOAI: oai:DiVA.org:liu-205279DiVA, id: diva2:1875297
External cooperation
Silo AI
Subject / course
Computer science
Supervisors
Examiners
Available from: 2024-07-10 Created: 2024-06-21 Last updated: 2025-02-07Bibliographically approved

Open Access in DiVA

fulltext(4233 kB)2323 downloads
File information
File name FULLTEXT01.pdfFile size 4233 kBChecksum SHA-512
6815217e5e8f0b181f95e3b4e850eae03c1255134558ddfbed4662930a9ac664b3a42e362edb05e4112a52dd8a7f6f741ef8ceab0534e2e251b2e46745afb9d6
Type fulltextMimetype application/pdf

Search in DiVA

By author/editor
Björk, HugoAndersson, Axel
By organisation
Department of Computer and Information Science
Natural Language Processing

Search outside of DiVA

GoogleGoogle Scholar
Total: 2326 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

urn-nbn

Altmetric score

urn-nbn
Total: 1582 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf